Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer

04/17/2018
by   Juncen Li, et al.
0

We consider the task of text attribute transfer: transforming a sentence to alter a specific attribute (e.g., sentiment) while preserving its attribute-independent content (e.g., changing "screen is just the right size" to "screen is too small"). Our training data includes only sentences labeled with their attribute (e.g., positive or negative), but not pairs of sentences that differ only in their attributes, so we must learn to disentangle attributes from attribute-independent content in an unsupervised way. Previous work using adversarial methods has struggled to produce high-quality outputs. In this paper, we propose simpler methods motivated by the observation that text attributes are often marked by distinctive phrases (e.g., "too small"). Our strongest method extracts content words by deleting phrases associated with the sentence's original attribute value, retrieves new phrases associated with the target attribute, and uses a neural model to fluently combine these into a final output. On human evaluation, our best method generates grammatical and appropriate responses on 22 averaged over three attribute transfer datasets: altering sentiment of reviews on Yelp, altering sentiment of reviews on Amazon, and altering image captions to be more romantic or humorous.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/21/2019

"Mask and Infill" : Applying Masked Language Model to Sentiment Transfer

This paper focuses on the task of sentiment transfer on non-parallel tex...
research
11/10/2019

Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles

Text style transfer is usually performed using attributes that can take ...
research
09/26/2019

Rethinking Text Attribute Transfer: A Lexical Analysis

Text attribute transfer is modifying certain linguistic attributes (e.g....
research
08/22/2018

Learning Sentiment Memories for Sentiment Modification without Parallel Data

The task of sentiment modification requires reversing the sentiment of t...
research
11/03/2018

Content preserving text generation with attribute controls

In this work, we address the problem of modifying textual attributes of ...
research
01/31/2019

Towards Controlled Transformation of Sentiment in Sentences

An obstacle to the development of many natural language processing produ...
research
08/26/2019

Rethinking Attribute Representation and Injection for Sentiment Classification

Text attributes, such as user and product information in product reviews...

Please sign up or login with your details

Forgot password? Click here to reset